CoCoRL learns safe constraints from demonstrations with unknown rewards.
problem Learning safe constraints from demonstrations with different unknown rewards.
method Convex Constraint Learning for Reinforcement Learning (CoCoRL) constructs a convex safe set based on demonstrations.
result CoCoRL learns constraints that lead to safe driving behavior and can safely transfer to different tasks and environments.
SafePILCO is a Python tool for safe reinforcement learning.
problem Safe and efficient policy synthesis in reinforcement learning.
method Extends PILCO algorithm with safety features, implemented in Python.
result Safe and data-efficient policy synthesis achieved.
New approach to reinforcement learning that balances safety and performance against adversaries.
problem Balancing safety and performance in reinforcement learning against potential adversaries.
method Developed a new reinforcement learning framework that integrates interruptibility, resilience, and safe exploration.
result Achieved both interruptibility and resilience to adversaries without sacrificing optimal policy probability.
Safe learning of stochastic dynamics with safety constraints.
problem Learning controlled stochastic dynamics with safety constraints.
method Iterative expansion of a safe control set using kernel-based confidence bounds.
result The method ensures safe exploration and efficient estimation of system dynamics.
Study on neural networks to identify redundancy issues in safe machine learning.
problem Identifying redundancy in neural network architectures for safe machine learning.
method Experiments with MNIST database using neural network classifiers.
result Underlines difficulties in using neural network classifiers for safe systems.
Safe screening reduces the number of triplets in metric learning.
problem Optimizing a metric over many triplets is computationally expensive and impractical.
method Safe triplet screening identifies and removes redundant triplets.
result Safe triplet screening maintains optimality without increasing computational cost.
Proposes a method to accelerate safe sequential learning using offline data.
problem Limited exploration due to disconnected safe regions and slow task learning.
method Safe transfer sequential learning using Gaussian processes and offline data.
result Enhances global exploration across multiple disjoint safe regions with lower data consumption.
Safe reinforcement learning for autonomous vehicles using prediction constraints.
problem Safe reinforcement learning for safety-critical applications like autonomous vehicles.
method Use prediction to constrain exploration in reinforcement learning models.
result Successfully learned intersection handling behaviors on an autonomous vehicle.
Robust regression model for safe exploration in control problems.
problem Learning and exploring safely in sequential control problems.
method Deep robust regression model trained to predict uncertainty bounds.
result Empirically outperforms conventional GP-based safe exploration.
OSIL learns safe policies from unsafe demonstrations.
problem Offline safe imitation learning with implicit safety.
method Formulates CMDP, infers safety from non-preferred trajectories, learns cost model.
result OSIL learns safer policies without degrading reward performance.
Safe exploration framework for IML algorithms.
problem Safe decision-making in IML without unsafe outcomes.
method Exploits Gaussian process prior to efficiently learn safe decisions.
result Outperforms other algorithms empirically.
Meta-learning priors improves safe Bayesian optimization.
problem Optimizing robot controllers under safety constraints.
method Meta-learning priors from offline data using F-PACOH.
result Meta-learned priors accelerate safe BO convergence.
Safe linear stochastic bandits ensure safe exploration with optimal regret.
problem Ensuring safe exploration in stochastic bandits while minimizing regret.
method Combining known safe arms with exploratory arms to safely expand the set of safe arms over time.
result The algorithm achieves an expected regret of O ( T log ( T ) ) O(\sqrt{T}\log (T)) O ( T log ( T )) . Revel tackles safe exploration in RL with verified symbolic policies.
problem Computational infeasibility of verifying neural networks in RL learning loops.
method Two policy classes: neurosymbolic with approximate gradients and symbolic policies for efficient verification. Mirror descent over policies to safely update and project policies.
result Revel discovers policies that outperform prior approaches to verified exploration.
Framework for safe reinforcement learning using expert demonstrations.
problem Ensuring safe behavior in reinforcement learning with unknown reward functions.
method Combines expert demonstrations with optimization methods to find safe reward functions.
result Trained agent safely avoids harmful states while mimicking expert behavior.
ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.
problem Balancing exploration and safety in unknown MDPs with stochastic dynamics.
method Exploits analogies between state-action pairs to safely learn near-optimal policies.
result Empirically improves sample efficiency compared to existing methods.
This paper introduces dynamic safe interruptibility for multi-agent reinforcement learning.
problem Preventing dangerous situations in decentralized multi-agent reinforcement learning.
method Introduces dynamic safe interruptibility, studies it in two learning frameworks, and gives sufficient conditions for its implementation.
result Dynamic safe interruptibility can be enabled for joint action learners but not for independent learners.
WiseMove framework for safe deep RL in autonomous driving.
problem Ensuring safety in deep reinforcement learning for autonomous driving.
method Modular learning architecture for motion planning.
result Demonstrated on a common traffic scenario, WiseMove supports safe learning.
SAMBA improves safe reinforcement learning with active exploration metrics.
problem Safe reinforcement learning in dynamic systems.
method Combines probabilistic modelling, information theory, and statistics. Uses novel metrics for out-of-sample Gaussian process evaluation.
result Orders of magnitude reduction in samples and violations compared to state-of-the-art methods.
Safe RL with binary feedback using SABRE algorithm.
problem Safe reinforcement learning with binary safety feedback.
method SABRE algorithm, combining active learning and reinforcement learning.
result Provable safe policy with high probability, no unsafe actions during training.
Safe reinforcement learning framework using optimal transport for robustness.
problem Robustness and safety in deep reinforcement learning with limited data assumptions.
method Optimal transport perturbations to construct worst-case virtual state transitions.
result Significantly improved safety at deployment time compared to standard methods.
Safe-M 3 ^3 3 -UCRL learns safe policies for multi-agent systems with global constraints.
problem Global constraints in mean-field reinforcement learning for multi-agent systems.
method Safe-M 3 ^3 3 -UCRL uses epistemic uncertainty and log-barrier approach to ensure constraints satisfaction. result Safe-M 3 ^3 3 -UCRL learns safe policies for multi-agent systems with global constraints. Quantum model improves safety in machine learning.
problem Improving safety and robustness in machine learning models.
method Variational quantum classifier with amplitude encoding and SAFE-AI metrics.
result Quantum model provides competitive performance and improved robustness.
SRF learns sparse rule models by screening out features efficiently.
problem Learning optimal sparse rule models is computationally intractable due to the large number of possible rules.
method SRF uses meta safe screening (mSS) to efficiently screen out multiple features, improving the learning of sparse rule models.
result SRF provides a general framework for fitting sparse rule models and can handle group regularization.
Safe imitation learning with a safety layer for flexible training.
problem Flexible yet safe imitation learning for complex tasks.
method Theory and modular method with a safety layer for continuous policy, adversarial training, and worst-case safety guarantees.
result Robustness advantage of safety layer during training compared to test time.
Safe actions learned in finite trials, without infinite exploration.
problem Learning safe actions in unknown environments efficiently.
method Defining a handicap metric and using sequential probability ratio test for discarding unsafe actions.
result Achieves constant handicap, discarding unsafe machines with probability one in finite rounds.
Safe autonomous decisions made with machine learning predictions using Conformal Decision Theory.
problem Safe decisions from imperfect machine learning predictions.
method Conformal Decision Theory framework for producing safe decisions.
result Safe decisions with provable statistical guarantees of low risk.
Safe learning for optimal control with known and unknown dynamics.
problem Safe learning of control strategies for systems with unknown dynamics.
method Reachability analysis and Gaussian Process regression for updating disturbances.
result Algorithm learns optimal control policies without violating safety constraints.
Safe reinforcement learning with nonconvex constraints using convex approximations.
problem Safe reinforcement learning with nonlinear function approximation.
method Constructing surrogate convex constrained optimization problems by replacing nonconvex functions with convex quadratic functions.
result Solutions to surrogate problems converge to a stationary point of the original nonconvex problem.
Risk-averse model uncertainty framework for safe reinforcement learning.
problem Safe decision making in uncertain environments.
method Risk-averse perspective towards model uncertainty using coherent distortion risk measures; equivalent to distributionally robust safe reinforcement learning problems; efficient, model-free implementation.
result Demonstrates robust performance and safety across perturbed test environments.
A method uses a supervisor policy to train a new policy safely and quickly for robots.
problem Training a new control policy safely and quickly for robots.
method Weighted average of supervisor and learned policies, pioneer network to compensate.
result Demonstrated effectiveness in OpenAI Gym experiments.
New method provides scalable safety guarantees for RL agents.
problem Safe reinforcement learning in real-life scenarios.
method State-augmentation and shield design for probabilistic avoidance.
result Strict formal safety guarantees for RL agents, scalable and practical.
Safe reinforcement learning with logical constraints for optimal policy synthesis.
problem Ensuring safety during reinforcement learning while maximizing goal satisfaction.
method Adaptive safe padding that synthesizes optimal control policies satisfying temporal logic formulas.
result The proposed method handles the trade-off between exploration and safety with theoretical guarantees.
Safe reinforcement learning with stability guarantees for real-world systems.
problem Lack of safety guarantees in reinforcement learning for real-world applications.
method Combines control theory with statistical models to ensure stability and safety.
result Proven ability to safely optimize neural network policies without system failure.
Safe semi-supervised learning for SPNs improves performance without degrading.
problem Expensive class annotations and abundant unlabelled data.
method Semi-supervised parameter learning for Sum-Product Networks (SPNs) that guarantees safe learning.
result SPNs can improve generative and discriminative objectives without degrading performance.
Paper improves safe policy improvement with estimated baseline policy.
problem Unreliable batch Reinforcement Learning algorithms in real-world applications.
method Apply SPIBB algorithms with an estimated baseline policy.
result Safe policy improvement guarantees over true baseline without direct access.
The paper uses temporal logic to guide safe reinforcement learning for complex tasks.
problem Learning safe control policies for complex, long-horizon tasks in physical systems.
method Combines temporal logic, control barrier functions, and control Lyapunov functions to facilitate safe exploration and learning.
result Developed a flexible system that allows users to specify task objectives and constraints in various forms and levels.
Paper defines ε-Safe Decision Regions for exponential family distributions and approximates them for unbalanced data.
problem Need probabilistic guarantees for reliable predictions in machine learning.
method Formalizes ε-Safe Decision Regions, proves their form for exponential family distributions, and develops Multi Cost SVM for unbalanced data.
result Formal definition and analytical determination of ε-Safe Decision Regions for exponential family distributions.
The problem of learning a sparse model is conceptually interpreted as the process of identifying active features/samples and then optimizing the model over them. Recently introduced safe screening allows us to identify a part of non-active features/samples. So far, safe screening has been individually studied either fo…
BubbleRank improves online search results using safe exploration.
problem Learning user preferences from scratch in online ranking is costly and risky.
method BubbleRank combines offline and online learning, starting with an initial base list and improving it online by exchanging items.
result BubbleRank achieves a graceful degradation of n-step regret with a good initial base list.
Safe learning in uncertain systems with state measurements and optimization.
problem Safe learning in nonlinear control-affine systems with unknown additive uncertainty.
method Model uncertainty as Gaussian noise, learn mean and covariance, use optimization to adjust control input.
result Guaranteed safety with arbitrarily large probability while learning and control proceed simultaneously.
New method tackles safe reinforcement learning from offline data.
problem Learn optimal policies from fixed data while adhering to safety constraints.
method Combines offline RL with online optimization to minimize cumulative cost.
result Proves approximate optimality of the approach under certain conditions.
Safe RL in linear systems achieves T \sqrt{T} T -regret.
problem Efficiently learning in safety-constrained online reinforcement learning.
method Study of linear quadratic regulator with safety constraints.
result First safe algorithm with i l d e O T ( T ) ilde{O}_T(\sqrt{T}) i l d e O T ( T ) -regret. Safe screening rules improve variable selection speed in high-dimensional regression.
problem Efficiently selecting important variables in high-dimensional regression problems.
method Developing Gap Safe screening rules for generalized linear models with sparsity enforcing penalties.
result Significant speed-ups in variable selection compared to previous methods on various learning tasks.
Exploration-exploitation of functions, that is learning and optimizing a mapping between inputs and expected outputs, is ubiquitous to many real world situations. These situations sometimes require us to avoid certain outcomes at all cost, for example because they are poisonous, harmful, or otherwise dangerous. We test…
Safe neural networks for input-output specifications.
problem Ensuring machine learning models adhere to input-output constraints.
method Designing constrained predictors and combining them safely.
result Demonstrated on synthetic and real-world datasets.
Safe Bayesian optimization method using information theory.
problem Optimizing unknown functions while respecting safety constraints.
method Information-theoretic exploration criterion for continuous domains.
result The method learns the value of the safe optimum up to arbitrary precision.
New algorithm for safe bandits with unknown parameters and constraints.
problem Safety-critical systems with unknown parameters and constraints.
method Safe-LUCB algorithm with two phases: pure exploration and safe exploration-exploitation.
result General and problem-dependent regret bounds for the Safe-LUCB algorithm.